{
  "best_metric": 1.0969889163970947,
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
  "epoch": 0.15625,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00625,
      "grad_norm": 1.8498634099960327,
      "learning_rate": 5e-06,
      "loss": 4.5813,
      "step": 1
    },
    {
      "epoch": 0.00625,
      "eval_loss": 1.2194494009017944,
      "eval_runtime": 18.6921,
      "eval_samples_per_second": 14.445,
      "eval_steps_per_second": 1.819,
      "step": 1
    },
    {
      "epoch": 0.0125,
      "grad_norm": 1.8300238847732544,
      "learning_rate": 1e-05,
      "loss": 4.3592,
      "step": 2
    },
    {
      "epoch": 0.01875,
      "grad_norm": 2.127028703689575,
      "learning_rate": 1.5e-05,
      "loss": 5.1297,
      "step": 3
    },
    {
      "epoch": 0.025,
      "grad_norm": 1.9777432680130005,
      "learning_rate": 2e-05,
      "loss": 5.1958,
      "step": 4
    },
    {
      "epoch": 0.03125,
      "grad_norm": 2.015655279159546,
      "learning_rate": 2.5e-05,
      "loss": 4.7181,
      "step": 5
    },
    {
      "epoch": 0.0375,
      "grad_norm": 2.0624945163726807,
      "learning_rate": 3e-05,
      "loss": 5.4952,
      "step": 6
    },
    {
      "epoch": 0.04375,
      "grad_norm": 3.5970277786254883,
      "learning_rate": 3.5e-05,
      "loss": 5.2734,
      "step": 7
    },
    {
      "epoch": 0.05,
      "grad_norm": 2.0029900074005127,
      "learning_rate": 4e-05,
      "loss": 4.5544,
      "step": 8
    },
    {
      "epoch": 0.05625,
      "grad_norm": 1.8359339237213135,
      "learning_rate": 4.5e-05,
      "loss": 4.6155,
      "step": 9
    },
    {
      "epoch": 0.0625,
      "grad_norm": 2.2517831325531006,
      "learning_rate": 5e-05,
      "loss": 5.4694,
      "step": 10
    },
    {
      "epoch": 0.06875,
      "grad_norm": 1.879914402961731,
      "learning_rate": 5.500000000000001e-05,
      "loss": 4.2894,
      "step": 11
    },
    {
      "epoch": 0.075,
      "grad_norm": 1.739548683166504,
      "learning_rate": 6e-05,
      "loss": 4.2815,
      "step": 12
    },
    {
      "epoch": 0.08125,
      "grad_norm": 1.5380457639694214,
      "learning_rate": 6.500000000000001e-05,
      "loss": 4.3312,
      "step": 13
    },
    {
      "epoch": 0.0875,
      "grad_norm": 1.6644234657287598,
      "learning_rate": 7e-05,
      "loss": 4.7402,
      "step": 14
    },
    {
      "epoch": 0.09375,
      "grad_norm": 1.525267243385315,
      "learning_rate": 7.500000000000001e-05,
      "loss": 4.8961,
      "step": 15
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.6433475017547607,
      "learning_rate": 8e-05,
      "loss": 4.1454,
      "step": 16
    },
    {
      "epoch": 0.10625,
      "grad_norm": 1.6035125255584717,
      "learning_rate": 8.5e-05,
      "loss": 4.5186,
      "step": 17
    },
    {
      "epoch": 0.1125,
      "grad_norm": 1.508162260055542,
      "learning_rate": 9e-05,
      "loss": 4.481,
      "step": 18
    },
    {
      "epoch": 0.11875,
      "grad_norm": 1.4459158182144165,
      "learning_rate": 9.5e-05,
      "loss": 3.9967,
      "step": 19
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.5539876222610474,
      "learning_rate": 0.0001,
      "loss": 4.7728,
      "step": 20
    },
    {
      "epoch": 0.13125,
      "grad_norm": 1.608622670173645,
      "learning_rate": 9.972609476841367e-05,
      "loss": 3.9576,
      "step": 21
    },
    {
      "epoch": 0.1375,
      "grad_norm": 1.5555155277252197,
      "learning_rate": 9.890738003669029e-05,
      "loss": 3.9051,
      "step": 22
    },
    {
      "epoch": 0.14375,
      "grad_norm": 1.7010705471038818,
      "learning_rate": 9.755282581475769e-05,
      "loss": 4.9004,
      "step": 23
    },
    {
      "epoch": 0.15,
      "grad_norm": 1.5186794996261597,
      "learning_rate": 9.567727288213005e-05,
      "loss": 4.1984,
      "step": 24
    },
    {
      "epoch": 0.15625,
      "grad_norm": 1.3770533800125122,
      "learning_rate": 9.330127018922194e-05,
      "loss": 3.8048,
      "step": 25
    },
    {
      "epoch": 0.15625,
      "eval_loss": 1.0969889163970947,
      "eval_runtime": 19.0256,
      "eval_samples_per_second": 14.191,
      "eval_steps_per_second": 1.787,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.492551407435776e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}